Few-shot Named Entity Recognition (NER) aims to identify named entities with
very little annotated data. Previous methods solve this problem based on
token-wise classification, which ignores the information of entity boundaries,
and inevitably the performance is affected by the massive non-entity tokens. To
this end, we propose a seminal span-based prototypical network (SpanProto) that
tackles few-shot NER via a two-stage approach, including span extraction and
mention classification. In the span extraction stage, we transform the
sequential tags into a global boundary matrix, enabling the model to focus on
the explicit boundary information. For mention classification, we leverage
prototypical learning to capture the semantic representations for each labeled
span and make the model better adapt to novel-class entities. To further
improve the model performance, we split out the false positives generated by
the span extractor but not labeled in the current episode set, and then present
a margin-based loss to separate them from each prototype region. Experiments
over multiple benchmarks demonstrate that our model outperforms strong
baselines by a large margin.

本文介绍了一种基于 SpanProto 和 prototypical learning 的 few-shot NER 方法，并使用 margin-based loss 进一步提高了模型性能。实验表明，该模型在多个基准测试中表现优异。